Akademik Veri Yönetim Sistemi
Green Energy and Technology, cilt.PartF2, ss.209-222, 2016 (Scopus)
In this study, wind energy potential of the campus of Mehmet Akif Ersoy University is analyzed by artificial neural networks (ANNs) with small data sets. For determining wind energy potential of the campus, a tower 63 m in height was built up. There were two anemometers for measuring of wind speed, at 30 m and 61 heights. Additionally, wind directions, pressure, temperature and humidity values were also measured with six different sensors. The energy required for the sensors mounted on the tower was supplied by 20 W photovoltaic panels. The measured data were modelled with ANNs to predict the long term wind parameters of the campus. Four different models were used for predicting the data with ANNs and a comparison of the models were done for determining the best one. The results showed that the statistical error values of training were obviously within acceptable uncertainties. Also the predicted values were very close to actual values.